ocertat/cmos
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

iter 1: preserve date qualifiers in web entries

Browse Source 
First real loop iteration found that GPT-5 silently drops date qualifiers
("Effective", "Published", "Accessed", etc.) when reformatting web
sources. The field diff was satisfied because the canonical date field
did not include the qualifier, but the canary exact-match axis caught
the regression.

Two fixes, per the canary-upstream policy:

1. Tighten the web-page exemplar canonical: date field now includes the
   "Effective" qualifier so the field diff will catch future regressions
   without relying on the canary.

2. Add SYSTEM_PROMPT rule 12 instructing the formatter to preserve
   semantic date qualifiers from the input.

After these fixes: scalar 1.000, canary exact-match 1.000 on all three
seed exemplars.
This commit is contained in:
cmos dev
2026-04-10 21:31:17 -04:00
parent ee0bcd107e
commit 1621d0d502
2 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
exemplars/web_page_google_privacy.toml
+5 -1
View File
@@ -12,5 +12,9 @@ expected_bibliography = "Google. \"Privacy Policy.\" Privacy & Terms. Effective
author = "Google"
title = "Privacy Policy"
site = "Privacy & Terms"
date = "November 15, 2023"
# Include the date qualifier ("Effective", "Published", "Accessed", etc.) in
# the canonical date field. CMOS 18 preserves these qualifiers in web-source
# entries; dropping them is a real regression even though the resulting
# string is structurally well-formed.
date = "Effective November 15, 2023"
url = "https://policies.google.com/privacy"